alphahg/CodeLllama-7b-rust-finetune-qlora

llama2-7b-rust-finetune

This model is a fine-tuned version of codellama/CodeLlama-7b-hf on the-stack-rust-clean dataset. It achieves the following results on the evaluation set:

• Loss: 0.5347

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2.5e-05
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 1
• training_steps: 500

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.0	100	0.5443
No log	0.01	200	0.5385
No log	0.01	300	0.5362
No log	0.01	400	0.5351
0.5389	0.02	500	0.5347

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1